{"id":1597668,"url":"https://alion.io/job/svitla-systems-gpu-ml-infrastructure-engineer-3","title":"GPU & ML Infrastructure Engineer","company":{"id":2216,"name":"Svitla Systems","domain":"svitla.com","url":"https://alion.io/company/svitla-systems","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Career site","truth_index":{"grade":"B","score":84,"open_postings":11,"ghost_share":0,"stale_share":0.636,"repost_share":0,"time_to_fill_p50_days":43,"computed_at":"2026-11-04T06:34:25Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":null,"work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"inferred_payroll_markers","remote_working_hours":{"label":"PST","utc_offset_min":-8,"utc_offset_max":-8},"hiring_geo_confidence":"inferred","locations":[],"countries":[],"hiring_countries":["US","AR","MX","CL"],"hiring_countries_total":4,"salary":null,"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Linux","optional":false},{"name":"LLM","optional":false},{"name":"Python","optional":false},{"name":"Time Series","optional":false},{"name":"NCCL","optional":true}],"status":"live","first_seen_at":"2026-08-06T08:30:48Z","employer_posted_date":"2026-08-06","last_verified_at":"2026-11-04T16:39:25Z","board_verified":true,"closed_at":null,"days_open":90,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":90},"description":"Svitla Systems Inc. is looking for a GPU & ML Infrastructure Engineer for a full-time position (40 hours per week) in the USA. Our client is a stealth startup. The successful candidate will own the end-to-end data generation process for GPU systems, including benchmark workloads, automated deployment, hardware telemetry collection, data quality validation, and dataset delivery. The role requires working with multiple NVIDIA data-center GPU generations and embedded or edge platforms.\nRequirements\nStrong experience deploying LLM inference and training workloads on GPUs, including quantized models.\nExperience diagnosing sensor, logging, and sampling issues in time-series hardware data.\nAbility to build reproducible GPU workloads and control sources of run-to-run variation.\nStrong Linux systems knowledge, including GPU driver stacks, process orchestration, scheduling, and timing.\nExperience collecting hardware telemetry programmatically using NVML, DCGM, BMC, IPMI, or Redfish.\nStrong Python skills for automation, telemetry collection, and data processing.\nExperience automating workload deployment and data collection across different hardware platforms.\nAbility to work independently and take ownership of technical processes.\nAvailability to overlap with the client’s team until 11:00 a.m. PST.\nNice to have\nExperience building data collection pipelines for hardware testing or systems research.\nFamiliarity with GPU benchmarking, stress testing, and benchmark methodology.\nKnowledge of GPU power, thermal management, multi-GPU scaling, and NCCL.\nExperience building automated data quality checks for time-series or sensor data.\nResponsibilities\nPort existing test procedures to new data-center GPUs and edge devices.\nBuild and maintain GPU benchmark workloads, including synthetic kernels and LLM inference and training.\nEnsure telemetry collection is accurate and consistent across platforms and data sources.\nInvestigate sampling issues, timestamp inconsistencies, missing sensor data, and logging anomalies.\nAutomate workload deployment, execution, data collection, and environment cleanup.\nBuild automated checks for missing samples, irregular intervals, clock mismatches, and invalid telemetry.\nDeliver datasets in a consistent and documented format with complete run metadata.\nDocument hardware targets, configurations, procedures, driver versions, and firmware versions.","description_format":"text","description_chars":2392,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"},{"name":"Argentina","iso":"AR","kind":"country"},{"name":"Mexico","iso":"MX","kind":"country"},{"name":"Chile","iso":"CL","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["DevOps & Platform Engineering","IT Outsourcing & Dedicated Teams","Custom Software Development"],"lifecycle":[{"event":"open","at":"2026-10-01T18:15:47Z"}],"visa":[{"country":"US","licensed_sponsor":true,"evidence":"Filed H-1B visas in the last two years","filings_12m":0,"filings_prev_12m":1,"green_card_filings_12m":0,"median_offered_wage_usd":null,"route":null,"cap_exempt":false,"checked_at":"2026-10-29T16:27:21+00:00","sources":["US Department of Labor: LCA disclosure data (H-1B, H-1B1, E-3)"],"filings_for_role_12m":0}],"liveness":{"score":11,"band":"cold","label":"Long shot","p_open":1,"p_active":0.382,"p_room":0.28,"age_days":89,"expected_fill_days":43,"reasons":["conf:4","stale_co","velocity","win:tail","crowd:"],"computed_at":"2026-11-04T06:34:25Z"},"pay":null,"html_url":"https://alion.io/job/svitla-systems-gpu-ml-infrastructure-engineer-3","json_url":"https://alion.io/job/svitla-systems-gpu-ml-infrastructure-engineer-3.json","meta":{"generated_at":"2026-11-04T19:11:17Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":29542,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-05T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":2216},"rest":"https://alion.io/mcp/rest/get_company?id=2216"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fsvitla-systems-gpu-ml-infrastructure-engineer-3"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fsvitla-systems-gpu-ml-infrastructure-engineer-3"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fsvitla-systems-gpu-ml-infrastructure-engineer-3"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/svitla-systems-gpu-ml-infrastructure-engineer-3\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fsvitla-systems-gpu-ml-infrastructure-engineer-3"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":1597668}},{"tool":"search_jobs","arguments":{"company":"svitla.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":1597668},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}